Leading-Edge Lip Sync Service Set to Transform In-Game Speech Development
You seriously have to watch the video.
Published: February 9, 2012
Speech Graphics Ltd. is an award winning start-up company based out of the United Kingdom. I doubt you know or have heard about their work but but don't be surprised if you start hearing a lot more about them. If you happen to be in the San Francisco area for the Game Developers Conference (March 7-9) be sure to stop by their booth. They will be showing off their newest tech which uniquely predicts how the muscles of the human face move to produce speech sounds.
The technology works using a universal physical model. Because of this, it can work across all languages which saves developers a whole lot of time and resources. If you stop by at GDC you can see them showing off seven languages: English, German, French, Spanish, Japanese, Korean and Russian.
"Speech is one of the most difficult things to animate convincingly, as the combination of fluidity and accuracy in natural speech is just so hard to capture in facial animation. People are very sensitive to this when you get it wrong because we are all focused on faces," said Michael Berger, CTO and co-founder of Speech Graphics. "With our technology we’re aiming for robust high quality, even better than what you can achieve with motion capture. And because it’s audio-driven, it’s at a price point that makes it scalable to huge amounts of speech.”
In this case, seeing is always better than reading. Check out the YouTube video below and prepare to have your cabbage blown back.
The technology works using a universal physical model. Because of this, it can work across all languages which saves developers a whole lot of time and resources. If you stop by at GDC you can see them showing off seven languages: English, German, French, Spanish, Japanese, Korean and Russian.
"Speech is one of the most difficult things to animate convincingly, as the combination of fluidity and accuracy in natural speech is just so hard to capture in facial animation. People are very sensitive to this when you get it wrong because we are all focused on faces," said Michael Berger, CTO and co-founder of Speech Graphics. "With our technology we’re aiming for robust high quality, even better than what you can achieve with motion capture. And because it’s audio-driven, it’s at a price point that makes it scalable to huge amounts of speech.”
In this case, seeing is always better than reading. Check out the YouTube video below and prepare to have your cabbage blown back.
